arch/nios2: add option to skip DMA sync as a part of map and unmap

This change allows us to pass DMA_ATTR_SKIP_CPU_SYNC which allows us to
avoid invoking cache line invalidation if the driver will just handle it
via a sync_for_cpu or sync_for_device call.

Link: http://lkml.kernel.org/r/20161110113518.76501.52225.stgit@ahduyck-blue-test.jf.intel.comSigned-off-by: NAlexander Duyck <alexander.h.duyck@intel.com>
Reviewed-by: NTobias Klauser <tklauser@distanz.ch>
Cc: Ley Foon Tan <lftan@altera.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

arch/nios2/mm/dma-mapping.c

@@ -98,13 +98,17 @@ static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	int i;
 
 	for_each_sg(sg, sg, nents, i) {
-		void *addr;
+		void *addr = sg_virt(sg);
 
-		addr = sg_virt(sg);
-		if (addr) {
-			__dma_sync_for_device(addr, sg->length, direction);
-			sg->dma_address = sg_phys(sg);
-		}
+		if (!addr)
+			continue;
+
+		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
+		__dma_sync_for_device(addr, sg->length, direction);
 	}
 
 	return nents;
@@ -117,7 +121,9 @@ static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page,
 {
 	void *addr = page_address(page) + offset;
 
-	__dma_sync_for_device(addr, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync_for_device(addr, size, direction);
+
 	return page_to_phys(page) + offset;
 }
 
@@ -125,7 +131,8 @@ static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 		size_t size, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
 }
 
 static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
@@ -138,6 +145,9 @@ static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	if (direction == DMA_TO_DEVICE)
 		return;
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	for_each_sg(sg, sg, nhwentries, i) {
 		addr = sg_virt(sg);
 		if (addr)